Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    famous and known

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     subalgebra
    0.72
    oyeva
    0.72
     SHOULD
    0.72
    摻
    0.72
     efectivamente
    0.70
    Percentages
    0.69
    อกาส
    0.69
     subpopulations
    0.67
     ვერ
    0.67
     Should
    0.67
    POSITIVE LOGITS
     known
    2.53
    known
    2.40
     famous
    2.35
     Known
    2.14
    Known
    2.13
     renowned
    2.13
     famed
    2.07
     conocido
    2.05
    famous
    1.99
     conhecido
    1.94
    Act Density 1.136%

    No Known Activations